{"data":{"slug":"tensorflow-hub","name":"hub","tagline":"A library for transfer learning by reusing parts of TensorFlow models.","github_url":"https://github.com/tensorflow/hub","owner":"tensorflow","repo":"hub","owner_avatar_url":"https://avatars.githubusercontent.com/u/15658638?v=4","primary_language":"Python","stars":3523,"forks":1641,"topics":["embeddings","image-classification","machine-learning","ml","python","tensorflow","transfer-learning"],"archived":false,"github_pushed_at":"2025-01-17T12:09:41+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/tensorflow-hub","markdown_url":"https://www.graphcanon.com/tools/tensorflow-hub.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorflow-hub","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorflow-hub","description":"A library for transfer learning by reusing parts of TensorFlow models.","homepage_url":"https://tensorflow.org/hub","license":"Apache-2.0","open_issues":6,"watchers":143,"ai_summary":"tensorflow/hub is a Python-based repository that facilitates the reuse of pre-trained model components via embeddings and supports various applications like image-classification, making it essential for machine-learning tasks involving transfer-learning techniques.","readme_excerpt":"## Getting Started\n\n  * [Introduction](https://www.tensorflow.org/hub/)\n  * The asset types of [tfhub.dev](https://tfhub.dev/)\n      * [SavedModels for TensorFlow 2](https://github.com/tensorflow/docs/blob/master/site/en/hub/tf2_saved_model.md)\n        and the [Reusable SavedModel interface](https://github.com/tensorflow/docs/blob/master/site/en/hub/reusable_saved_models.md).\n      * Deprecated: [Models in TF1 Hub format](https://github.com/tensorflow/docs/blob/master/site/en/hub/tf1_hub_module.md)\n        and their [Common Signatures](https://github.com/tensorflow/docs/blob/master/site/en/hub/common_signatures/index.md)\n        collection.\n  * Using the library\n      * [Installation](https://github.com/tensorflow/docs/blob/master/site/en/hub/installation.md)\n      * [Caching model downloads](https://github.com/tensorflow/docs/blob/master/site/en/hub/caching.md)\n      * [Migration to TF2](https://github.com/tensorflow/docs/blob/master/site/en/hub/migration_tf2.md)\n      * [Model compatibility for TF1/TF2](https://github.com/tensorflow/docs/blob/master/site/en/hub/model_compatibility.md)\n      * [Common issues](https://github.com/tensorflow/docs/blob/master/site/en/hub/common_issues.md)\n      * [Build from source](https://github.com/tensorflow/docs/blob/master/site/en/hub/build_from_source.md)\n      * [Hosting a module](https://github.com/tensorflow/docs/blob/master/site/en/hub/hosting.md)\n  * Tutorials\n      * [TF2 Image Retraining](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/hub/tutorials/tf2_image_retraining.ipynb)\n      * [TF2 Text Classification](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/hub/tutorials/tf2_text_classification.ipynb)\n      * [Additional TF1 and TF2 examples](examples/README.md)\n\n---\n\n## License\n\n[Apache License 2.0](LICENSE)","github_created_at":"2018-03-12T07:55:42+00:00","created_at":"2026-07-11T11:28:59.702202+00:00","updated_at":"2026-08-22T06:00:58.150211+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"embeddings","name":"embeddings"},{"slug":"image-classification","name":"image-classification"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"ml","name":"ml"},{"slug":"python","name":"python"},{"slug":"tensorflow","name":"tensorflow"},{"slug":"transfer-learning","name":"transfer-learning"}],"trust":{"provenance":{"is_fork":false,"github_id":124853261,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T06:00:57.377Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":581,"last_release_at":"2024-01-30T15:53:29Z","stars_delta_30d":1,"open_issues_delta_30d":-5},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:29:00.834Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T06:00:57.850Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-22T06:00:57.850Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-22T06:00:57.850Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The core functionalities of hub are free to use with an open-source license; however, additional services or enterprise support might incur costs."},"requirements":{"notes":["Requires a Python environment and TensorFlow installation to operate."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need to leverage existing TensorFlow models and integrate specific parts of them for tasks like embedding or image-classification without retraining the entire model from scratch.","If your project requires access to a diverse set of pre-trained TensorFlow modules readily available in the hub, streamlining transfer learning processes."],"when_not_to_use":["When working strictly with non-TensorFlow frameworks such as PyTorch or MXNet, as hub is built specifically for enhancing and reusing models within TensorFlow.","If your project requires a more generalized approach to machine-learning without reliance on pre-existing model components, focusing instead on training models from the ground up."],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:04:00.882Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The core functionalities of hub are free to use with an open-source license; however, additional services or enterprise support might incur costs."},{"label":"Requirements","value":"Requires a Python environment and TensorFlow installation to operate."},{"label":"Adopt for","value":"hub is specifically tailored to Python developers who wish to incorporate transfer learning into their TensorFlow projects with pre-trained model components for applications such as image classification."},{"label":"License detail","value":"hub is licensed under Apache-2.0, allowing for broad use in both open source and commercial projects."}]}}